node-llama-cpp 3.0.0-beta.4 → 3.0.0-beta.41

package/README.md

@@ -1,5 +1,5 @@
 <div align="center">
-    <img alt="node-llama-cpp Logo" src="https://media.githubusercontent.com/media/withcatai/node-llama-cpp/master/assets/logo.roundEdges.png" width="360px" />
+    <img alt="node-llama-cpp Logo" src="https://raw.githubusercontent.com/withcatai/node-llama-cpp/master/assets/logo.roundEdges.png" width="360px" />
     <h1>node-llama-cpp</h1>
     <p>Run AI models locally on your machine</p>
     <sub>Pre-built bindings are provided with a fallback to building from source with cmake</sub>
@@ -15,12 +15,12 @@
 
 </div>
 
-✨ New! [Try the beta of version `3.0.0`](https://github.com/withcatai/node-llama-cpp/pull/105) ✨ (included: function calling, automatic chat wrapper detection, and more)
+✨ New! [Try the beta of version `3.0.0`](https://github.com/withcatai/node-llama-cpp/pull/105) ✨ (included: function calling, automatic chat wrapper detection, embedding support, and more)
 
 ## Features
 * Run a text generation model locally on your machine
-* Metal and CUDA support
-* Pre-built binaries are provided, with a fallback to building from source without `node-gyp` or Python
+* Metal, CUDA and Vulkan support
+* Pre-built binaries are provided, with a fallback to building from source _**without**_ `node-gyp` or Python
 * Chat with a model using a chat wrapper
 * Use the CLI to chat with a model without writing any code
 * Up-to-date with the latest version of `llama.cpp`. Download and compile the latest release with a single CLI command.
@@ -47,15 +47,18 @@ To disable this behavior set the environment variable `NODE_LLAMA_CPP_SKIP_DOWNL
 ```typescript
 import {fileURLToPath} from "url";
 import path from "path";
-import {LlamaModel, LlamaContext, LlamaChatSession} from "node-llama-cpp";
+import {getLlama, LlamaChatSession} from "node-llama-cpp";
 
 const __dirname = path.dirname(fileURLToPath(import.meta.url));
 
-const model = new LlamaModel({
-    modelPath: path.join(__dirname, "models", "codellama-13b.Q3_K_M.gguf")
+const llama = await getLlama();
+const model = await llama.loadModel({
+    modelPath: path.join(__dirname, "models", "dolphin-2.1-mistral-7b.Q4_K_M.gguf")
+});
+const context = await model.createContext();
+const session = new LlamaChatSession({
+    contextSequence: context.getSequence()
 });
-const context = new LlamaContext({model});
-const session = new LlamaChatSession({context});
 
 
 const q1 = "Hi there, how are you?";
@@ -65,7 +68,7 @@ const a1 = await session.prompt(q1);
 console.log("AI: " + a1);
 
 
-const q2 = "Summerize what you said";
+const q2 = "Summarize what you said";
 console.log("User: " + q2);
 
 const a2 = await session.prompt(q2);
@@ -84,7 +87,7 @@ To contribute to `node-llama-cpp` read the [contribution guide](https://withcata
 <br />
 
 <div align="center" width="360">
-    <img alt="Star please" src="https://media.githubusercontent.com/media/withcatai/node-llama-cpp/master/assets/star.please.roundEdges.png" width="360" margin="auto" />
+    <img alt="Star please" src="https://raw.githubusercontent.com/withcatai/node-llama-cpp/master/assets/star.please.roundEdges.png" width="360" margin="auto" />
     <br/>
     <p align="right">
         <i>If you like this repo, star it ✨</i>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;

package/bins/_linux-x64-cuda.moved.txt

@@ -0,0 +1 @@
+Moved to package "@node-llama-cpp/linux-x64-cuda"

package/bins/_win-x64-cuda.moved.txt

@@ -0,0 +1 @@
+Moved to package "@node-llama-cpp/win-x64-cuda"

package/bins/linux-arm64/_nlcBuildMetadata.json

@@ -0,0 +1 @@
+{"buildOptions":{"customCmakeOptions":{},"progressLogs":true,"platform":"linux","platformInfo":{"name":"Ubuntu","version":"22.04"},"arch":"arm64","gpu":false,"llamaCpp":{"repo":"ggerganov/llama.cpp","release":"b3504"}}}

package/bins/linux-armv7l/_nlcBuildMetadata.json

@@ -0,0 +1 @@
+{"buildOptions":{"customCmakeOptions":{},"progressLogs":true,"platform":"linux","platformInfo":{"name":"Ubuntu","version":"22.04"},"arch":"armv7l","gpu":false,"llamaCpp":{"repo":"ggerganov/llama.cpp","release":"b3504"}}}

package/bins/linux-x64/_nlcBuildMetadata.json

@@ -0,0 +1 @@
+{"buildOptions":{"customCmakeOptions":{},"progressLogs":true,"platform":"linux","platformInfo":{"name":"Ubuntu","version":"22.04"},"arch":"x64","gpu":false,"llamaCpp":{"repo":"ggerganov/llama.cpp","release":"b3504"}}}

package/bins/linux-x64-vulkan/_nlcBuildMetadata.json

@@ -0,0 +1 @@
+{"buildOptions":{"customCmakeOptions":{},"progressLogs":true,"platform":"linux","platformInfo":{"name":"Ubuntu","version":"22.04"},"arch":"x64","gpu":"vulkan","llamaCpp":{"repo":"ggerganov/llama.cpp","release":"b3504"}}}

package/bins/mac-arm64-metal/_nlcBuildMetadata.json

@@ -0,0 +1 @@
+{"buildOptions":{"customCmakeOptions":{},"progressLogs":true,"platform":"mac","platformInfo":{"name":"macOS","version":"22.6.0"},"arch":"arm64","gpu":"metal","llamaCpp":{"repo":"ggerganov/llama.cpp","release":"b3504"}}}